English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Object recognition in humans depends primarily on shape cues. We havedeveloped a new approach to measuring the shape recognition performance of avision system based on nearest neighbor view matching within the system'sembedding space. Our performance benchmark, ShapeY, allows for precise controlof task difficulty, by enforcing that view matching span a specified degree of3D viewpoint change and/or appearance change. As a first test case we measuredthe performance of ResNet50 pre-trained on ImageNet. Matching error rates werehigh. For example, a 27 degree change in object pitch led ResNet50 to match theincorrect object 45% of the time. Appearance changes were also highlydisruptive. Examination of false matches indicates that ResNet50's embeddingspace is severely "tangled". These findings suggest ShapeY can be a useful toolfor charting the progress of artificial vision systems towards human-levelshape recognition capabilities.

ShapeY: Measuring Shape Recognition Capacity Using Nearest Neighbor Matching